Papers
arxiv:2409.06166

Revisiting Prompt Pretraining of Vision-Language Models

Published on Sep 10, 2024
Authors:
,
,
,
,

Abstract

A prompt pretraining framework improves the fitting and generalization of vision-language models by using separate query, key, and value prompts and CLIP-derived soft labels, producing more transferable prompt initialization.

Prompt learning is an effective method to customize Vision-Language Models (VLMs) for various downstream tasks, involving tuning very few parameters of input prompt tokens. Recently, prompt pretraining in large-scale dataset (e.g., ImageNet-21K) has played a crucial role in prompt learning for universal visual discrimination. However, we revisit and observe that the limited learnable prompts could face underfitting risks given the extensive images during prompt pretraining, simultaneously leading to poor generalization. To address the above issues, in this paper, we propose a general framework termed Revisiting Prompt Pretraining (RPP), which targets at improving the fitting and generalization ability from two aspects: prompt structure and prompt supervision. For prompt structure, we break the restriction in common practice where query, key, and value vectors are derived from the shared learnable prompt token. Instead, we introduce unshared individual query, key, and value learnable prompts, thereby enhancing the model's fitting capacity through increased parameter diversity. For prompt supervision, we additionally utilize soft labels derived from zero-shot probability predictions provided by a pretrained Contrastive Language Image Pretraining (CLIP) teacher model. These soft labels yield more nuanced and general insights into the inter-class relationships, thereby endowing the pretraining process with better generalization ability. RPP produces a more resilient prompt initialization, enhancing its robust transferability across diverse visual recognition tasks. Experiments across various benchmarks consistently confirm the state-of-the-art (SOTA) performance of our pretrained prompts. Codes and models will be made available soon.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2409.06166
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2409.06166 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2409.06166 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2409.06166 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.